Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add mathiasbourgoin/roster --skill arch-index-orientgit clone --depth 1 https://github.com/mathiasbourgoin/rosterWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/mathiasbourgoin/roster/arch-index-orient)<a href="https://agentmods.dev/skills/mathiasbourgoin/roster/arch-index-orient"><img src="https://agentmods.dev/badge/skills/mathiasbourgoin/roster/arch-index-orient/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/mathiasbourgoin/roster/arch-index-orient"><img src="https://agentmods.dev/badge/skills/mathiasbourgoin/roster/arch-index-orient.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00041 | $0.00809 |
| Opus 5 | $0.00020 | $0.00404 |
| Sonnet 5 | $0.00008 | $0.00162 |
| Haiku 4.5 | $0.00004 | $0.00081 |
Grade A, and why
arch-index-orient scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured today.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 68 lines — stays where its author put it; the contents beside it link to each section on GitHub.
arch-index-orient
Orientation provider for roster-research (never a QA gate — provides is
research-orientation, not gate). orient.sh emits JSON row-objects on
stdout, read-only against the SQLite index at .arch-index/index.db (built
by arch-index-init — never regenerated here).
The first content line of every successful (exit-0) invocation is the mandatory index-freshness header:
<!-- index-freshness: <index.db mtime, ISO-8601 UTC> vs HEAD <commit short> -->
so consumers can see when the index is stale relative to HEAD before trusting a graph hit — this is advisory only, never a gate.
Modes
bash orient.sh <mode> [args...], dispatched by $1:
callees <sym>— symbols<sym>calls (callsrows wherecaller = <sym>).callers <sym>— symbols that call<sym>(callsrows wherecallee = <sym>).fan-in— symbols ranked by incoming-caller count (GROUP BY callee).definition <sym>— thesymbolsrow for<sym>(empty array if absent).path <A> <B>— a depth-bounded path fromAtoBovercalls, via a recursive CTE with a simple-path guard (instrexcludes any node already on the walk's accumulated path) plus an explicit depth-counter cap as a secondary bound.UNIONalone only dedupes identical (node, path, level) rows and is not sufficient for cycle safety on branching/cyclic graphs; the simple-path guard is what actually terminates.A == Breturns a trivial zero-length result; no path returns an empty array — both exit 0, never an error. Bounded by a 120s timeout (coreutilstimeout, when on PATH) on direct invocation too, matching the resolver's own bound.
Every result set is capped by TOP_N/LIMIT (default 10).
Steps
- The consumer (
scripts/code-intel-resolve.js orient <mode> [args...]) invokesbash orient.sh <mode> [args...]from the project root. - Degradation checks, each a distinct exit-3 reason token on stderr,
verdict-neutral: index DB absent →
index-missing; neitherarch-indexnorsqlite3on PATH →tool-missing; the DB lackscallsorsymbols→schema-mismatch: <table> not found. - On success, the freshness header prints first, then the mode's JSON rows.
- This pack relies ONLY on
calls(caller, callee)andsymbols(name, visibility, comment_quality_score)— no other table or column is referenced, so an upstream schema change degrades gracefully instead of breaking.
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- today First seen · 68 lines · 41 tokens per session scan A 1b2a0a3e6c76
arch-index-orient is a skill published in the GitHub repository mathiasbourgoin/roster (2 stars, last pushed yesterday), licensed MIT. It adds 41 tokens to every session and 809 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-12.
Other skills, from other repositories
adversarial-reviewer
Adversarial code review that assumes bugs exist and hunts for them. Use when asked to review code, find bugs, audit for correctness, stress-test a PR, or when someone says "tear this apart" or "what's wrong with this". Give no benefit of the doubt — every line is guilty until proven innocent.
gsd-ns-review
Route to the appropriate quality / review skill based on the user's intent. gsd-code-review-fix was absorbed by gsd-code-review --fix in #2790.
issue
Use when starting a chain from a GitHub issue — turning an issue URL or number into a triaged, planned, dispatched, and reviewed pull request. Classifies the thread (bug → root-cause discipline, feature → plan chain, question → drafted reply), synthesizes a spec from the issue's own acceptance criteria, then runs the…
gitnexus
A code-graph analysis add-on for examining an existing codebase, including symbols, call paths, execution flows, and effects across repositories. It can query GitNexus through its command-line or MCP interfaces.
cleanup-code-inspections
Reduce technical debt and improve code quality by systematically resolving static analysis warnings.
sonarqube-mcp
Provides SonarQube and SonarCloud integration patterns via the Model Context Protocol (MCP) server. Enables quality gate monitoring, issue discovery and triaging, pre-push code analysis, and rule education directly in the agent workflow. Use when the user wants to check quality gates, search for Sonar issues, analyze…